{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6437311172485352, "min": 0.589735746383667, "max": 1.416475534439087, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19456.12890625, "min": 17871.3515625, "max": 42970.203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29932.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29932.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.10817890614271164, "min": -0.11651916056871414, "max": 0.42530879378318787, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 26.612010955810547, "min": -27.964597702026367, "max": 113.98275756835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -2.345491409301758, "min": -6.10516357421875, "max": 0.7415123581886292, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -576.9909057617188, "min": -1587.342529296875, "max": 175.73843383789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06801167780017633, "min": 0.06424098359263827, "max": 0.07313633597782339, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9521634892024687, "min": 0.5671326788547745, "max": 1.0412892848835327, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 1.6556923260940994, "min": 0.00020093872507229304, "max": 4.762759036118431, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 23.179692565317392, "min": 0.0026122034259398095, "max": 66.67862650565803, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.636640311628573e-06, "min": 7.636640311628573e-06, "max": 0.00029520945159685, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010691296436280003, "min": 0.00010691296436280003, "max": 0.0033825284724906, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025455142857143, "min": 0.1025455142857143, "max": 0.19840314999999997, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356372000000002, "min": 1.4356372000000002, "max": 2.5275094000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002642968771428573, "min": 0.0002642968771428573, "max": 0.009840474685, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003700156280000002, "min": 0.003700156280000002, "max": 0.11277818906, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010438172146677971, "min": 0.010438172146677971, "max": 0.5317188501358032, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1461344063282013, "min": 0.1461344063282013, "max": 4.253750801086426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 737.6666666666666, "min": 428.4848484848485, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30982.0, "min": 15964.0, "max": 32595.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.40496663021899404, "min": -0.9999500522390008, "max": 1.493170126827795, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 17.00859846919775, "min": -31.998401671648026, "max": 100.04239849746227, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.40496663021899404, "min": -0.9999500522390008, "max": 1.493170126827795, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 17.00859846919775, "min": -31.998401671648026, "max": 100.04239849746227, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07992272592881429, "min": 0.058543632732618055, "max": 11.119983524084091, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3567544890102, "min": 3.066087754406908, "max": 177.91973638534546, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744080477", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744083718" }, "total": 3240.9060520580006, "count": 1, "self": 0.6403814500008593, "children": { "run_training.setup": { "total": 0.031606990000000224, "count": 1, "self": 0.031606990000000224 }, "TrainerController.start_learning": { "total": 3240.2340636179997, "count": 1, "self": 2.3978963479539743, "children": { "TrainerController._reset_env": { "total": 4.642176391000248, "count": 1, "self": 4.642176391000248 }, "TrainerController.advance": { "total": 3233.096982283045, "count": 63571, "self": 2.527847131189901, "children": { "env_step": { "total": 2121.3593254409366, "count": 63571, "self": 1952.393461039646, "children": { "SubprocessEnvManager._take_step": { "total": 167.60579144116355, "count": 63571, "self": 7.028123955101364, "children": { "TorchPolicy.evaluate": { "total": 160.57766748606218, "count": 62582, "self": 160.57766748606218 } } }, "workers": { "total": 1.3600729601271269, "count": 63571, "self": 0.0, "children": { "worker_root": { "total": 3232.524142706056, "count": 63571, "is_parallel": true, "self": 1457.1967202419896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00427604899959988, "count": 1, "is_parallel": true, "self": 0.0015468520000467834, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027291969995530962, "count": 8, "is_parallel": true, "self": 0.0027291969995530962 } } }, "UnityEnvironment.step": { "total": 0.06599142000004576, "count": 1, "is_parallel": true, "self": 0.0006435420004891057, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000536389999979292, "count": 1, "is_parallel": true, "self": 0.000536389999979292 }, "communicator.exchange": { "total": 0.06270738099965456, "count": 1, "is_parallel": true, "self": 0.06270738099965456 }, "steps_from_proto": { "total": 0.0021041069999228057, "count": 1, "is_parallel": true, "self": 0.0004156020004302263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016885049994925794, "count": 8, "is_parallel": true, "self": 0.0016885049994925794 } } } } } } }, "UnityEnvironment.step": { "total": 1775.3274224640663, "count": 63570, "is_parallel": true, "self": 45.2519477369824, "children": { "UnityEnvironment._generate_step_input": { "total": 30.362613214020257, "count": 63570, "is_parallel": true, "self": 30.362613214020257 }, "communicator.exchange": { "total": 1574.09652253602, "count": 63570, "is_parallel": true, "self": 1574.09652253602 }, "steps_from_proto": { "total": 125.6163389770436, "count": 63570, "is_parallel": true, "self": 27.742648085165456, "children": { "_process_rank_one_or_two_observation": { "total": 97.87369089187814, "count": 508560, "is_parallel": true, "self": 97.87369089187814 } } } } } } } } } } }, "trainer_advance": { "total": 1109.2098097109183, "count": 63571, "self": 4.715605532756399, "children": { "process_trajectory": { "total": 165.89719800016928, "count": 63571, "self": 165.57008659516987, "children": { "RLTrainer._checkpoint": { "total": 0.32711140499941394, "count": 2, "self": 0.32711140499941394 } } }, "_update_policy": { "total": 938.5970061779926, "count": 451, "self": 367.0871505170544, "children": { "TorchPPOOptimizer.update": { "total": 571.5098556609382, "count": 22803, "self": 571.5098556609382 } } } } } } }, "trainer_threads": { "total": 1.2090004020137712e-06, "count": 1, "self": 1.2090004020137712e-06 }, "TrainerController._save_models": { "total": 0.09700738700030342, "count": 1, "self": 0.001938148000590445, "children": { "RLTrainer._checkpoint": { "total": 0.09506923899971298, "count": 1, "self": 0.09506923899971298 } } } } } } }